@inproceedings{singh-etal-2023-entity,
title = "Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding",
author = "Singh, Janvijay and
Bai, Fan and
Wang, Zhen",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.90",
doi = "10.18653/v1/2023.eacl-main.90",
pages = "1255--1263",
abstract = "Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct formulation, i.e., tracking the event flow while following structural constraints. State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results. To this end, we propose MeeT, a Multi-task learning-enabled entity Tracking approach, which utilizes knowledge gained from general domain tasks to improve entity tracking. Specifically, MeeT first fine-tunes T5, a pre-trained multi-task learning model, with entity tracking-specialized QA formats, and then employs our customized decoding strategy to satisfy the structural constraints. MeeT achieves state-of-the-art performances on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2023-entity">
<titleInfo>
<title>Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janvijay</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct formulation, i.e., tracking the event flow while following structural constraints. State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results. To this end, we propose MeeT, a Multi-task learning-enabled entity Tracking approach, which utilizes knowledge gained from general domain tasks to improve entity tracking. Specifically, MeeT first fine-tunes T5, a pre-trained multi-task learning model, with entity tracking-specialized QA formats, and then employs our customized decoding strategy to satisfy the structural constraints. MeeT achieves state-of-the-art performances on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.</abstract>
<identifier type="citekey">singh-etal-2023-entity</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.90</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.90</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1255</start>
<end>1263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding
%A Singh, Janvijay
%A Bai, Fan
%A Wang, Zhen
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F singh-etal-2023-entity
%X Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct formulation, i.e., tracking the event flow while following structural constraints. State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results. To this end, we propose MeeT, a Multi-task learning-enabled entity Tracking approach, which utilizes knowledge gained from general domain tasks to improve entity tracking. Specifically, MeeT first fine-tunes T5, a pre-trained multi-task learning model, with entity tracking-specialized QA formats, and then employs our customized decoding strategy to satisfy the structural constraints. MeeT achieves state-of-the-art performances on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.
%R 10.18653/v1/2023.eacl-main.90
%U https://aclanthology.org/2023.eacl-main.90
%U https://doi.org/10.18653/v1/2023.eacl-main.90
%P 1255-1263
Markdown (Informal)
[Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding](https://aclanthology.org/2023.eacl-main.90) (Singh et al., EACL 2023)
ACL